Iliya Kulbaka
Papers
3
Total Citations
8
H-Index
2
About
Iliya Kulbaka is a researcher at the intersection of robotics, artificial intelligence, and environmental sensing, with a core focus on autonomous gas detection and mapping. His work addresses the critical challenge of enabling mobile robots to efficiently locate and map airborne chemical sources using deep reinforcement learning. Kulbaka’s key contributions include the development of novel algorithms that combine deep Q-learning with recurrent neural networks, such as CNN-LSTM architectures, to guide robot navigation under real-world constraints like limited battery life. His most notable paper, “GDM-Net,” introduces a framework that integrates deep reinforcement learning with Gaussian Process regression for gas distribution mapping, enabling robots to intelligently sample an area without exhaustive coverage. With over 8 citations across his top papers, Kulbaka’s research is gaining traction for its practical impact on hazardous environment monitoring, industrial safety, and pollution control. His work on energy-constrained coverage and deep recurrent Q-learning represents a significant step toward deploying autonomous robots for real-time chemical source localization, a task with profound implications for disaster response and environmental protection.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3